Class: TrieveRubyClient::ChunkData
- Inherits:
-
Object
- Object
- TrieveRubyClient::ChunkData
- Defined in:
- lib/trieve_ruby_client/models/chunk_data.rb
Instance Attribute Summary collapse
-
#chunk_html ⇒ Object
HTML content of the chunk.
-
#chunk_vector ⇒ Object
Chunk_vector is a vector of floats which can be used instead of generating a new embedding.
-
#convert_html_to_text ⇒ Object
Convert HTML to raw text before processing to avoid adding noise to the vector embeddings.
-
#group_ids ⇒ Object
Group ids are the ids of the groups that the chunk should be placed into.
-
#group_tracking_ids ⇒ Object
Group tracking_ids are the tracking_ids of the groups that the chunk should be placed into.
-
#image_urls ⇒ Object
Image urls are a list of urls to images that are associated with the chunk.
-
#link ⇒ Object
Link to the chunk.
-
#location ⇒ Object
Returns the value of attribute location.
-
#metadata ⇒ Object
Metadata is a JSON object which can be used to filter chunks.
-
#split_avg ⇒ Object
Split avg is a boolean which tells the server to split the text in the chunk_html into smaller chunks and average their resulting vectors.
-
#tag_set ⇒ Object
Tag set is a list of tags.
-
#time_stamp ⇒ Object
Time_stamp should be an ISO 8601 combined date and time without timezone.
-
#tracking_id ⇒ Object
Tracking_id is a string which can be used to identify a chunk.
-
#upsert_by_tracking_id ⇒ Object
Upsert when a chunk with the same tracking_id exists.
-
#weight ⇒ Object
Weight is a float which can be used to bias search results.
Class Method Summary collapse
-
._deserialize(type, value) ⇒ Object
Deserializes the data based on type.
-
.acceptable_attributes ⇒ Object
Returns all the JSON keys this model knows about.
-
.attribute_map ⇒ Object
Attribute mapping from ruby-style variable name to JSON key.
-
.build_from_hash(attributes) ⇒ Object
Builds the object from hash.
-
.openapi_nullable ⇒ Object
List of attributes with nullable: true.
-
.openapi_types ⇒ Object
Attribute type mapping.
Instance Method Summary collapse
-
#==(o) ⇒ Object
Checks equality by comparing each attribute.
-
#_to_hash(value) ⇒ Hash
Outputs non-array value in the form of hash For object, use to_hash.
- #eql?(o) ⇒ Boolean
-
#hash ⇒ Integer
Calculates hash code according to all attributes.
-
#initialize(attributes = {}) ⇒ ChunkData
constructor
Initializes the object.
-
#list_invalid_properties ⇒ Object
Show invalid properties with the reasons.
-
#to_body ⇒ Hash
to_body is an alias to to_hash (backward compatibility).
-
#to_hash ⇒ Hash
Returns the object in the form of hash.
-
#to_s ⇒ String
Returns the string representation of the object.
-
#valid? ⇒ Boolean
Check to see if the all the properties in the model are valid.
Constructor Details
#initialize(attributes = {}) ⇒ ChunkData
Initializes the object
132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 132 def initialize(attributes = {}) if (!attributes.is_a?(Hash)) fail ArgumentError, "The input argument (attributes) must be a hash in `TrieveRubyClient::ChunkData` initialize method" end # check to see if the attribute exists and convert string to symbol for hash key attributes = attributes.each_with_object({}) { |(k, v), h| if (!self.class.attribute_map.key?(k.to_sym)) fail ArgumentError, "`#{k}` is not a valid attribute in `TrieveRubyClient::ChunkData`. Please check the name to make sure it's valid. List of attributes: " + self.class.attribute_map.keys.inspect end h[k.to_sym] = v } if attributes.key?(:'chunk_html') self.chunk_html = attributes[:'chunk_html'] end if attributes.key?(:'chunk_vector') if (value = attributes[:'chunk_vector']).is_a?(Array) self.chunk_vector = value end end if attributes.key?(:'convert_html_to_text') self.convert_html_to_text = attributes[:'convert_html_to_text'] end if attributes.key?(:'group_ids') if (value = attributes[:'group_ids']).is_a?(Array) self.group_ids = value end end if attributes.key?(:'group_tracking_ids') if (value = attributes[:'group_tracking_ids']).is_a?(Array) self.group_tracking_ids = value end end if attributes.key?(:'image_urls') if (value = attributes[:'image_urls']).is_a?(Array) self.image_urls = value end end if attributes.key?(:'link') self.link = attributes[:'link'] end if attributes.key?(:'location') self.location = attributes[:'location'] end if attributes.key?(:'metadata') self. = attributes[:'metadata'] end if attributes.key?(:'split_avg') self.split_avg = attributes[:'split_avg'] end if attributes.key?(:'tag_set') if (value = attributes[:'tag_set']).is_a?(Array) self.tag_set = value end end if attributes.key?(:'time_stamp') self.time_stamp = attributes[:'time_stamp'] end if attributes.key?(:'tracking_id') self.tracking_id = attributes[:'tracking_id'] end if attributes.key?(:'upsert_by_tracking_id') self.upsert_by_tracking_id = attributes[:'upsert_by_tracking_id'] end if attributes.key?(:'weight') self.weight = attributes[:'weight'] end end |
Instance Attribute Details
#chunk_html ⇒ Object
HTML content of the chunk. This can also be plaintext. The innerText of the HTML will be used to create the embedding vector. The point of using HTML is for convienience, as some users have applications where users submit HTML content.
19 20 21 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 19 def chunk_html @chunk_html end |
#chunk_vector ⇒ Object
Chunk_vector is a vector of floats which can be used instead of generating a new embedding. This is useful for when you are using a pre-embedded dataset. If this is not provided, the innerText of the chunk_html will be used to create the embedding.
22 23 24 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 22 def chunk_vector @chunk_vector end |
#convert_html_to_text ⇒ Object
Convert HTML to raw text before processing to avoid adding noise to the vector embeddings. By default this is true. If you are using HTML content that you want to be included in the vector embeddings, set this to false.
25 26 27 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 25 def convert_html_to_text @convert_html_to_text end |
#group_ids ⇒ Object
Group ids are the ids of the groups that the chunk should be placed into. This is useful for when you want to create a chunk and add it to a group or multiple groups in one request. Necessary because this route queues the chunk for ingestion and the chunk may not exist yet immediately after response.
28 29 30 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 28 def group_ids @group_ids end |
#group_tracking_ids ⇒ Object
Group tracking_ids are the tracking_ids of the groups that the chunk should be placed into. This is useful for when you want to create a chunk and add it to a group or multiple groups in one request. Necessary because this route queues the chunk for ingestion and the chunk may not exist yet immediately after response.
31 32 33 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 31 def group_tracking_ids @group_tracking_ids end |
#image_urls ⇒ Object
Image urls are a list of urls to images that are associated with the chunk. This is useful for when you want to associate images with a chunk.
34 35 36 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 34 def image_urls @image_urls end |
#link ⇒ Object
Link to the chunk. This can also be any string. Frequently, this is a link to the source of the chunk. The link value will not affect the embedding creation.
37 38 39 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 37 def link @link end |
#location ⇒ Object
Returns the value of attribute location.
39 40 41 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 39 def location @location end |
#metadata ⇒ Object
Metadata is a JSON object which can be used to filter chunks. This is useful for when you want to filter chunks by arbitrary metadata. Unlike with tag filtering, there is a performance hit for filtering on metadata.
42 43 44 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 42 def @metadata end |
#split_avg ⇒ Object
Split avg is a boolean which tells the server to split the text in the chunk_html into smaller chunks and average their resulting vectors. This is useful for when you want to create a chunk from a large piece of text and want to split it into smaller chunks to create a more fuzzy average dense vector. The sparse vector will be generated normally with no averaging. By default this is false.
45 46 47 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 45 def split_avg @split_avg end |
#tag_set ⇒ Object
Tag set is a list of tags. This can be used to filter chunks by tag. Unlike with metadata filtering, HNSW indices will exist for each tag such that there is not a performance hit for filtering on them.
48 49 50 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 48 def tag_set @tag_set end |
#time_stamp ⇒ Object
Time_stamp should be an ISO 8601 combined date and time without timezone. It is used for time window filtering and recency-biasing search results.
51 52 53 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 51 def time_stamp @time_stamp end |
#tracking_id ⇒ Object
Tracking_id is a string which can be used to identify a chunk. This is useful for when you are coordinating with an external system and want to use the tracking_id to identify the chunk.
54 55 56 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 54 def tracking_id @tracking_id end |
#upsert_by_tracking_id ⇒ Object
Upsert when a chunk with the same tracking_id exists. By default this is false, and the request will fail if a chunk with the same tracking_id exists. If this is true, the chunk will be updated if a chunk with the same tracking_id exists.
57 58 59 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 57 def upsert_by_tracking_id @upsert_by_tracking_id end |
#weight ⇒ Object
Weight is a float which can be used to bias search results. This is useful for when you want to bias search results for a chunk. The magnitude only matters relative to other chunks in the chunk’s dataset dataset.
60 61 62 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 60 def weight @weight end |
Class Method Details
._deserialize(type, value) ⇒ Object
Deserializes the data based on type
292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 292 def self._deserialize(type, value) case type.to_sym when :Time Time.parse(value) when :Date Date.parse(value) when :String value.to_s when :Integer value.to_i when :Float value.to_f when :Boolean if value.to_s =~ /\A(true|t|yes|y|1)\z/i true else false end when :Object # generic object (usually a Hash), return directly value when /\AArray<(?<inner_type>.+)>\z/ inner_type = Regexp.last_match[:inner_type] value.map { |v| _deserialize(inner_type, v) } when /\AHash<(?<k_type>.+?), (?<v_type>.+)>\z/ k_type = Regexp.last_match[:k_type] v_type = Regexp.last_match[:v_type] {}.tap do |hash| value.each do |k, v| hash[_deserialize(k_type, k)] = _deserialize(v_type, v) end end else # model # models (e.g. Pet) or oneOf klass = TrieveRubyClient.const_get(type) klass.respond_to?(:openapi_any_of) || klass.respond_to?(:openapi_one_of) ? klass.build(value) : klass.build_from_hash(value) end end |
.acceptable_attributes ⇒ Object
Returns all the JSON keys this model knows about
84 85 86 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 84 def self.acceptable_attributes attribute_map.values end |
.attribute_map ⇒ Object
Attribute mapping from ruby-style variable name to JSON key.
63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 63 def self.attribute_map { :'chunk_html' => :'chunk_html', :'chunk_vector' => :'chunk_vector', :'convert_html_to_text' => :'convert_html_to_text', :'group_ids' => :'group_ids', :'group_tracking_ids' => :'group_tracking_ids', :'image_urls' => :'image_urls', :'link' => :'link', :'location' => :'location', :'metadata' => :'metadata', :'split_avg' => :'split_avg', :'tag_set' => :'tag_set', :'time_stamp' => :'time_stamp', :'tracking_id' => :'tracking_id', :'upsert_by_tracking_id' => :'upsert_by_tracking_id', :'weight' => :'weight' } end |
.build_from_hash(attributes) ⇒ Object
Builds the object from hash
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 268 def self.build_from_hash(attributes) return nil unless attributes.is_a?(Hash) attributes = attributes.transform_keys(&:to_sym) transformed_hash = {} openapi_types.each_pair do |key, type| if attributes.key?(attribute_map[key]) && attributes[attribute_map[key]].nil? transformed_hash["#{key}"] = nil elsif type =~ /\AArray<(.*)>/i # check to ensure the input is an array given that the attribute # is documented as an array but the input is not if attributes[attribute_map[key]].is_a?(Array) transformed_hash["#{key}"] = attributes[attribute_map[key]].map { |v| _deserialize($1, v) } end elsif !attributes[attribute_map[key]].nil? transformed_hash["#{key}"] = _deserialize(type, attributes[attribute_map[key]]) end end new(transformed_hash) end |
.openapi_nullable ⇒ Object
List of attributes with nullable: true
110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 110 def self.openapi_nullable Set.new([ :'chunk_html', :'chunk_vector', :'convert_html_to_text', :'group_ids', :'group_tracking_ids', :'image_urls', :'link', :'location', :'metadata', :'split_avg', :'tag_set', :'time_stamp', :'tracking_id', :'upsert_by_tracking_id', :'weight' ]) end |
.openapi_types ⇒ Object
Attribute type mapping.
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 89 def self.openapi_types { :'chunk_html' => :'String', :'chunk_vector' => :'Array<Float>', :'convert_html_to_text' => :'Boolean', :'group_ids' => :'Array<String>', :'group_tracking_ids' => :'Array<String>', :'image_urls' => :'Array<String>', :'link' => :'String', :'location' => :'GeoInfo', :'metadata' => :'Object', :'split_avg' => :'Boolean', :'tag_set' => :'Array<String>', :'time_stamp' => :'String', :'tracking_id' => :'String', :'upsert_by_tracking_id' => :'Boolean', :'weight' => :'Float' } end |
Instance Method Details
#==(o) ⇒ Object
Checks equality by comparing each attribute.
233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 233 def ==(o) return true if self.equal?(o) self.class == o.class && chunk_html == o.chunk_html && chunk_vector == o.chunk_vector && convert_html_to_text == o.convert_html_to_text && group_ids == o.group_ids && group_tracking_ids == o.group_tracking_ids && image_urls == o.image_urls && link == o.link && location == o.location && == o. && split_avg == o.split_avg && tag_set == o.tag_set && time_stamp == o.time_stamp && tracking_id == o.tracking_id && upsert_by_tracking_id == o.upsert_by_tracking_id && weight == o.weight end |
#_to_hash(value) ⇒ Hash
Outputs non-array value in the form of hash For object, use to_hash. Otherwise, just return the value
363 364 365 366 367 368 369 370 371 372 373 374 375 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 363 def _to_hash(value) if value.is_a?(Array) value.compact.map { |v| _to_hash(v) } elsif value.is_a?(Hash) {}.tap do |hash| value.each { |k, v| hash[k] = _to_hash(v) } end elsif value.respond_to? :to_hash value.to_hash else value end end |
#eql?(o) ⇒ Boolean
255 256 257 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 255 def eql?(o) self == o end |
#hash ⇒ Integer
Calculates hash code according to all attributes.
261 262 263 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 261 def hash [chunk_html, chunk_vector, convert_html_to_text, group_ids, group_tracking_ids, image_urls, link, location, , split_avg, tag_set, time_stamp, tracking_id, upsert_by_tracking_id, weight].hash end |
#list_invalid_properties ⇒ Object
Show invalid properties with the reasons. Usually used together with valid?
218 219 220 221 222 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 218 def list_invalid_properties warn '[DEPRECATED] the `list_invalid_properties` method is obsolete' invalid_properties = Array.new invalid_properties end |
#to_body ⇒ Hash
to_body is an alias to to_hash (backward compatibility)
339 340 341 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 339 def to_body to_hash end |
#to_hash ⇒ Hash
Returns the object in the form of hash
345 346 347 348 349 350 351 352 353 354 355 356 357 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 345 def to_hash hash = {} self.class.attribute_map.each_pair do |attr, param| value = self.send(attr) if value.nil? is_nullable = self.class.openapi_nullable.include?(attr) next if !is_nullable || (is_nullable && !instance_variable_defined?(:"@#{attr}")) end hash[param] = _to_hash(value) end hash end |
#to_s ⇒ String
Returns the string representation of the object
333 334 335 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 333 def to_s to_hash.to_s end |
#valid? ⇒ Boolean
Check to see if the all the properties in the model are valid
226 227 228 229 |
# File 'lib/trieve_ruby_client/models/chunk_data.rb', line 226 def valid? warn '[DEPRECATED] the `valid?` method is obsolete' true end |